9 March 2010 3D reconstruction of the optic nerve head using stereo fundus images for computer-aided diagnosis of glaucoma
Author Affiliations +
Abstract
The shape of the optic nerve head (ONH) is reconstructed automatically using stereo fundus color images by a robust stereo matching algorithm, which is needed for a quantitative estimate of the amount of nerve fiber loss for patients with glaucoma. Compared to natural scene stereo, fundus images are noisy because of the limits on illumination conditions and imperfections of the optics of the eye, posing challenges to conventional stereo matching approaches. In this paper, multi scale pixel feature vectors which are robust to noise are formulated using a combination of both pixel intensity and gradient features in scale space. Feature vectors associated with potential correspondences are compared with a disparity based matching score. The deep structures of the optic disc are reconstructed with a stack of disparity estimates in scale space. Optical coherence tomography (OCT) data was collected at the same time, and depth information from 3D segmentation was registered with the stereo fundus images to provide the ground truth for performance evaluation. In experiments, the proposed algorithm produces estimates for the shape of the ONH that are close to the OCT based shape, and it shows great potential to help computer-aided diagnosis of glaucoma and other related retinal diseases.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Li Tang, Young H. Kwon, Wallace L. M. Alward, Emily C. Greenlee, Kyungmoo Lee, Mona K. Garvin, Michael D. Abràmoff, "3D reconstruction of the optic nerve head using stereo fundus images for computer-aided diagnosis of glaucoma", Proc. SPIE 7624, Medical Imaging 2010: Computer-Aided Diagnosis, 76243D (9 March 2010); doi: 10.1117/12.843912; https://doi.org/10.1117/12.843912
PROCEEDINGS
8 PAGES


SHARE
Back to Top